System

Abstract

An object of a system according to an embodiment is to generate text that reflects the characteristics of a character selected by a user.SOLUTION: A system includes a reception unit, a collection unit, a learning unit, a pre-processing unit, and a post-processing unit. The receiving unit receives character selection from a user. The collecting unit collects data indicating the characteristics of the character selected by the receiving unit. The learning unit learns the characteristics of the character on the basis of the data collected by the collection unit. The preprocessing unit performs preprocessing of text generation on the basis of the feature learned by the learning unit. The post-processor performs post-processing on the text generated by the preprocessor.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology had the problem that the text generated by the AI ​​did not adequately reflect the characteristics of the characters that users preferred.

[0005] The system according to the embodiment aims to generate text that reflects the characteristics of a character selected by a user. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a collection unit, a learning unit, a preprocessing unit, and a postprocessing unit. The reception unit receives character selection from a user. The collection unit collects data indicating characteristics of the character selected by the reception unit. The learning unit learns the character's characteristics based on the data collected by the collection unit. The preprocessing unit performs preprocessing for text generation based on the characteristics learned by the learning unit. The postprocessing unit performs postprocessing on the text generated by the preprocessing unit. [Effects of the Invention]

[0007] The system according to the embodiment can generate text that reflects the characteristics of a character selected by a user. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A text generation system according to an embodiment of the present invention generates text in the tone of a character selected by a user. The text generation system learns the characteristics of the character selected by the user and reflects the character's characteristics in the generated text. For example, the text generation system allows a user to select a favorite character and collect lines from entertainment works in which the character appears. The collected lines are then included in a generation AI, which then learns the character's characteristics based on these lines. Next, preprocessing of the text generation is performed to reflect the character's characteristics in the generated results. Furthermore, postprocessing is performed on the generated text to emphasize the character's characteristics and add character-specific phrases and emotional expressions. This allows users to generate text in the tone of their favorite character's speech. The text generation system can also earn revenue by receiving optional usage fees for the generation AI from users. This allows the text generation system to generate text in the tone of a character selected by the user. For example, users can enjoy generating text in the tone of their favorite character's speech. Furthermore, service providers can earn revenue by receiving optional usage fees for the generation AI from users. For example, various pricing plans can be offered, such as monthly fees or fees based on the number of uses.

[0029] A text generation system according to an embodiment includes a reception unit, a collection unit, a learning unit, a preprocessing unit, and a postprocessing unit. The reception unit receives a character selection from a user. The user can select a favorite character, such as a character from an entertainment work. The collection unit collects data indicating characteristics of the selected character. For example, the collection unit collects lines of the character from entertainment works. The collection unit can collect lines from, for example, anime dialogue or game scenarios. The learning unit learns the character's characteristics based on the collected data. For example, the learning unit learns the character's tone and speaking style based on the collected lines. The learning unit learns the character's characteristics using a generation AI. The preprocessing unit performs preprocessing for text generation based on the learned characteristics. For example, the preprocessing unit provides specific instructions to the generation AI to reflect the character's characteristics. The postprocessing unit performs postprocessing on the generated text. For example, the postprocessing unit adds character-specific phrases and emotional expressions to the generated text. This allows the text generation system according to the embodiment to generate text in the tone of voice of the character selected by the user.

[0030] The text generation system includes a revenue unit that receives optional usage fees for the generation AI from users. The revenue unit receives optional usage fees for the generation AI from users. For example, the revenue unit can offer various pricing plans, such as monthly fees or fees based on the number of uses. This allows the service provider to earn revenue by receiving optional usage fees for the generation AI from users.

[0031] The collection unit can collect lines of characters from entertainment works. The collection unit collects lines from, for example, anime lines or game scenarios. For example, the collection unit collects anime lines and uses them as training data for the generation AI. The collection unit can also collect lines from game scenarios and use them as training data for the generation AI. Furthermore, the collection unit can collect lines from movie scripts and use them as training data for the generation AI. This makes it possible to generate text that reflects the characteristics of the characters.

[0032] The learning unit can learn the character's tone of voice and speaking style based on the collected lines. The learning unit, for example, learns the character's tone of voice and speaking style based on the collected lines. For example, the learning unit learns the character's unique phrases and speaking patterns. The learning unit can also learn the character's emotional expressions and writing style. Furthermore, the learning unit can learn the character's pronunciation and intonation. In this way, the character's characteristics can be learned and reflected in text generation.

[0033] The preprocessing unit can give specific instructions to the generation AI to reflect the characteristics of the character. The preprocessing unit can, for example, give specific instructions to the generation AI to reflect the characteristics of the character. For example, the preprocessing unit can give instructions to the generation AI to reflect the character's tone and speaking style. The preprocessing unit can also give instructions to the generation AI to reflect the character's unique phrases and emotional expressions. Furthermore, the preprocessing unit can also give instructions to the generation AI to reflect the character's writing style and pronunciation. This allows the generated text to better reflect the character's characteristics.

[0034] The post-processing unit can add character-specific phrases and emotional expressions to the generated text. For example, the post-processing unit can add character-specific phrases and emotional expressions to the generated text. For example, the post-processing unit can add character-specific phrases. The post-processing unit can also add character emotional expressions. Furthermore, the post-processing unit can emphasize the characteristics of the character's tone and speaking style. This makes the generated text more character-like.

[0035] The reception unit can analyze the user's past character selection history and recommend the most suitable character. The reception unit, for example, analyzes the user's past character selection history and recommends the most suitable character. For example, the reception unit may preferentially display characters that the user has frequently selected in the past. The reception unit can also recommend characters that are appropriate for a specific time period or situation based on the user's past selection history. Furthermore, the reception unit can automatically suggest highly relevant characters based on the user's past selection history. This makes it possible to recommend the most suitable character based on the user's past selection history.

[0036] The reception unit can filter characters based on the user's current interests and trends when selecting a character. For example, the reception unit can display related characters based on keywords recently searched by the user. The reception unit can also analyze the user's social media activities and recommend characters that match current trends. Furthermore, the reception unit can filter characters based on trends in online communities in which the user participates. This allows characters to be filtered based on the user's interests and trends.

[0037] The reception unit can provide an optimal selection means according to the user's input method when selecting a character. For example, the reception unit can provide an optimal selection means according to the user's input method when selecting a character. For example, when the user uses voice input, the reception unit can use voice recognition technology to enable the user to select a character. Furthermore, when the user uses text input, the reception unit can search for and display characters based on input keywords. Furthermore, when the user uses image input, the reception unit can use image recognition technology to identify characters and display them as options. This makes it possible to provide an optimal selection means according to the user's input method.

[0038] The reception unit can prioritize displaying highly relevant characters in consideration of the user's geographical location information when selecting a character. For example, the reception unit prioritizes displaying highly relevant characters in consideration of the user's geographical location information when selecting a character. For example, if the user is in a specific area, the reception unit can prioritize displaying characters related to that area. Furthermore, if the user is traveling, the reception unit can also prioritize displaying characters related to the travel destination. Furthermore, if the user is participating in a specific event, the reception unit can also prioritize displaying characters related to the event. In this way, highly relevant characters can be displayed based on the user's geographical location information.

[0039] The reception unit can analyze the user's social media activity and recommend related characters when selecting a character. For example, the reception unit can analyze the user's social media activity and recommend related characters when selecting a character. For example, the reception unit can preferentially display characters that the user follows on social media. The reception unit can also analyze the content of the user's social media posts and recommend related characters. Furthermore, the reception unit can recommend related characters by referring to the activities of the user's friends on social media. This makes it possible to recommend related characters based on the user's social media activity.

[0040] The reception unit can customize the selection method by reflecting the user's past feedback when selecting a character. For example, the reception unit customizes the selection method by reflecting the user's past feedback when selecting a character. For example, the reception unit preferentially displays characters that the user has previously rated highly. The reception unit can also customize the selection interface based on the user's past feedback. Furthermore, the reception unit can also display characters that the user has previously rated poorly, excluding such characters. This allows the selection method to be customized based on the user's past feedback.

[0041] The collection unit can select the optimal collection method depending on the type of entertainment work. The collection unit selects the optimal collection method depending on, for example, the type of entertainment work. For example, in the case of an anime, the collection unit collects lines based on subtitle data. In addition, in the case of a game, the collection unit can also collect lines based on scenario data. Furthermore, in the case of a movie, the collection unit can also collect lines based on script data. This makes it possible to select the optimal collection method depending on the type of entertainment work.

[0042] The collection unit can filter lines based on the scene and situation in which the character appears when collecting the lines. For example, the collection unit filters lines based on the scene and situation in which the character appears when collecting the lines. For example, the collection unit prioritizes collecting lines spoken by a character in an important scene. The collection unit can also prioritize collecting lines in scenes in which a character expresses a particular emotion. Furthermore, the collection unit can also prioritize collecting lines in scenes in which a character is conversing with other characters. This makes it possible to collect lines based on the scene and situation in which a character appears.

[0043] The collection unit can provide an optimal collection means depending on the user's input method when collecting lines. For example, the collection unit provides an optimal collection means depending on the user's input method when collecting lines. For example, when the user uses voice input, the collection unit collects lines using voice recognition technology. Also, when the user uses text input, the collection unit can search for and collect lines based on the input keywords. Furthermore, when the user uses image input, the collection unit can identify a character using image recognition technology and collect the character's lines. This makes it possible to provide an optimal collection means depending on the user's input method.

[0044] When collecting lines, the collection unit can prioritize collecting highly relevant lines by taking into account the user's geographical location information. For example, when collecting lines, the collection unit prioritizes collecting highly relevant lines by taking into account the user's geographical location information. For example, when the user is in a specific area, the collection unit can prioritize collecting lines related to that area. Also, when the user is traveling, the collection unit can prioritize collecting lines related to the travel destination. Furthermore, when the user is participating in a specific event, the collection unit can prioritize collecting lines related to the event. In this way, highly relevant lines can be collected based on the user's geographical location information.

[0045] The collection unit can analyze the user's social media activities and collect related lines when collecting lines. For example, the collection unit analyzes the user's social media activities and collects related lines when collecting lines. For example, the collection unit prioritizes collecting lines of characters the user follows on social media. The collection unit can also analyze the content of the user's social media posts and collect related lines. Furthermore, the collection unit can collect related lines by referring to the activities of the user's friends on social media. This makes it possible to collect related lines based on the user's social media activities.

[0046] The collection unit can customize the collection method by reflecting the user's past feedback when collecting lines. For example, the collection unit customizes the collection method by reflecting the user's past feedback when collecting lines. For example, the collection unit preferentially collects lines that the user has previously rated highly. The collection unit can also customize the collection interface based on the user's past feedback. Furthermore, the collection unit can also collect lines that the user has previously rated poorly, excluding these lines. This allows the collection method to be customized based on the user's past feedback.

[0047] The learning unit can optimize the learning algorithm by referring to past learning data during learning. For example, the learning unit optimizes the learning algorithm by referring to past learning data during learning. For example, the learning unit adjusts the parameters of the learning algorithm based on the past learning data. The learning unit can also extract effective learning patterns from the past learning data and reflect them in the algorithm. Furthermore, the learning unit can analyze the past learning data and improve the accuracy of the learning algorithm. This makes it possible to optimize the learning algorithm by referring to past learning data.

[0048] The learning unit can analyze changes in a character's tone of voice and speaking style during learning and update the learning data. For example, the learning unit analyzes changes in a character's tone of voice and speaking style during learning and update the learning data. For example, if a character's tone of voice changes, the learning unit reflects the change in the learning data. Also, if a character's speaking style changes, the learning unit can also reflect the change in the learning data. Furthermore, if a new line is added to the character, the learning unit can add the line to the learning data. This makes it possible to update the learning data in response to changes in a character's tone of voice and speaking style.

[0049] The learning unit can adjust the learning algorithm by reflecting user feedback during learning. For example, the learning unit adjusts the learning algorithm by reflecting user feedback during learning. For example, the learning unit adjusts the learning algorithm based on generation results that the user has given a high rating. The learning unit can also improve the learning algorithm based on generation results that the user has given a low rating. Furthermore, the learning unit can analyze user feedback and improve the accuracy of the learning algorithm. This makes it possible to adjust the learning algorithm based on user feedback.

[0050] The learning unit can weight the learning data based on the time of submission of the lines during learning. For example, the learning unit weights the learning data based on the time of submission of the lines during learning. For example, the learning unit weights the learning data by assigning a high weight to recently submitted lines. The learning unit can also weight older lines by assigning a low weight to older lines during learning. Furthermore, the learning unit can dynamically adjust the weight of lines based on the time of submission. This makes it possible to weight the learning data based on the time of submission of the lines.

[0051] The learning unit can integrate information from different data sources to expand the training data during training. For example, the learning unit can integrate information from different data sources to expand the training data during training. For example, the learning unit collects and integrates lines from different data sources such as anime, games, and movies. The learning unit can also expand the training data based on information from different data sources. Furthermore, the learning unit can integrate information from different data sources to improve the accuracy of the learning algorithm. This makes it possible to expand the training data by integrating information from different data sources.

[0052] The learning unit can improve the accuracy of learning by referring to literature related to the character during learning. For example, the learning unit can improve the accuracy of learning by referring to literature related to the character during learning. For example, the learning unit can complement the learning data by referring to official character setting materials. The learning unit can also adjust the learning algorithm based on literature related to the character. Furthermore, the learning unit can improve the accuracy of the learning data by referring to literature related to the character. As a result, the accuracy of learning is improved by referring to literature related to the character.

[0053] The pre-processing unit can perform filtering to emphasize the characteristics of a character's tone of voice and speaking style during pre-processing. The pre-processing unit, for example, performs filtering to emphasize the characteristics of a character's tone of voice and speaking style during pre-processing. For example, the pre-processing unit performs filtering to emphasize the unique tone of voice of a character. The pre-processing unit can also perform filtering to emphasize the characteristics of a character's speaking style. Furthermore, the pre-processing unit can also perform filtering to emphasize the emotional expressions of a character. This makes it possible to perform filtering to emphasize the characteristics of a character's tone of voice and speaking style.

[0054] During preprocessing, the preprocessing unit can provide instructions for generating text based on the scene and situation in which the character appears. During preprocessing, the preprocessing unit, for example, provides instructions for generating text based on the scene and situation in which the character appears. For example, the preprocessing unit provides instructions for generating text based on lines spoken by a character in an important scene. The preprocessing unit can also provide instructions for generating text based on lines spoken in a scene in which the character expresses a particular emotion. Furthermore, the preprocessing unit can also provide instructions for generating text based on lines spoken in a scene in which the character is conversing with another character. This makes it possible to provide instructions for generating text based on the scene and situation in which the character appears.

[0055] The preprocessing unit can improve the accuracy of preprocessing by referring to the user's past generation results during preprocessing. For example, the preprocessing unit improves the accuracy of preprocessing by referring to the user's past generation results during preprocessing. For example, the preprocessing unit improves the accuracy of preprocessing based on generation results that the user has given a high rating. The preprocessing unit can also improve the preprocessing method based on generation results that the user has given a low rating. Furthermore, the preprocessing unit can analyze the user's past generation results and improve the accuracy of preprocessing. In this way, the accuracy of preprocessing is improved by referring to the user's past generation results.

[0056] The preprocessing unit can provide instructions for text generation taking into account the geographical background of the character during preprocessing. For example, the preprocessing unit provides instructions for text generation taking into account the geographical background of the character during preprocessing. For example, the preprocessing unit provides instructions for text generation based on lines spoken by the character related to a specific region. Furthermore, if the character is traveling, the preprocessing unit can also provide instructions for text generation based on lines related to the travel destination. Furthermore, if the character is participating in a specific event, the preprocessing unit can also provide instructions for text generation based on lines related to the event. This makes it possible to provide instructions for text generation based on the geographical background of the character.

[0057] The preprocessing unit may improve the accuracy of the preprocessing by referring to literature related to the character during preprocessing. For example, the preprocessing unit may improve the accuracy of the preprocessing by referring to literature related to the character during preprocessing. For example, the preprocessing unit may improve the accuracy of the preprocessing by referring to official character setting materials. The preprocessing unit may also adjust the preprocessing method based on literature related to the character. Furthermore, the preprocessing unit may improve the accuracy of the preprocessing by referring to literature related to the character. In this way, the accuracy of the preprocessing is improved by referring to literature related to the character.

[0058] The preprocessing unit can adjust the preprocessing method during preprocessing, taking into account the market value of the character. For example, the preprocessing unit adjusts the preprocessing method during preprocessing, taking into account the market value of the character. For example, the preprocessing unit prioritizes preprocessing of lines of popular characters. The preprocessing unit can also prioritize preprocessing of lines of characters with high market value. Furthermore, the preprocessing unit can adjust the preprocessing method based on the market value of the character. This makes it possible to adjust the preprocessing method based on the market value of the character.

[0059] The post-processing unit can perform filtering during post-processing to emphasize phrases and emotional expressions unique to a character. For example, the post-processing unit performs filtering during post-processing to emphasize phrases and emotional expressions unique to a character. For example, the post-processing unit performs filtering to emphasize phrases unique to a character. The post-processing unit can also perform filtering to emphasize emotional expressions of a character. Furthermore, the post-processing unit can also perform filtering to emphasize the characteristics of a character's tone of voice or speaking style. This makes it possible to perform filtering to emphasize phrases and emotional expressions unique to a character.

[0060] The post-processing unit can modify the text during post-processing based on the scene and situation in which the character appears. For example, the post-processing unit modifies the text during post-processing based on the scene and situation in which the character appears. For example, the post-processing unit modifies the text based on lines spoken by the character in an important scene. The post-processing unit can also modify the text based on lines spoken in a scene in which the character expresses a particular emotion. Furthermore, the post-processing unit can also modify the text based on lines spoken in a scene in which the character is conversing with another character. This makes it possible to modify the text based on the scene and situation in which the character appears.

[0061] The post-processing unit can improve the accuracy of post-processing by referring to the user's past generation results during post-processing. For example, the post-processing unit improves the accuracy of post-processing by referring to the user's past generation results during post-processing. For example, the post-processing unit improves the accuracy of post-processing based on generation results that the user has given a high rating. The post-processing unit can also improve the post-processing method based on generation results that the user has given a low rating. Furthermore, the post-processing unit can analyze the user's past generation results and improve the accuracy of post-processing. In this way, the accuracy of post-processing is improved by referring to the user's past generation results.

[0062] The post-processing unit can modify text during post-processing, taking into account the geographical background of the character. For example, the post-processing unit modifies text during post-processing, taking into account the geographical background of the character. For example, the post-processing unit modifies text based on lines that the character has spoken related to a specific region. In addition, if the character is traveling, the post-processing unit can also modify text based on lines that are related to the travel destination. Furthermore, if the character is participating in a specific event, the post-processing unit can also modify text based on lines that are related to the event. This makes it possible to modify text based on the geographical background of the character.

[0063] The post-processing unit may improve the accuracy of post-processing by referring to literature related to the character during post-processing. For example, the post-processing unit may improve the accuracy of post-processing by referring to literature related to the character during post-processing. For example, the post-processing unit may improve the accuracy of post-processing by referring to official character setting materials. The post-processing unit may also adjust the post-processing method based on the literature related to the character. Furthermore, the post-processing unit may improve the accuracy of post-processing by referring to literature related to the character. In this way, the accuracy of post-processing is improved by referring to literature related to the character.

[0064] The post-processing unit can adjust the post-processing method during post-processing, taking into account the market value of the character. For example, the post-processing unit adjusts the post-processing method during post-processing, taking into account the market value of the character. For example, the post-processing unit prioritizes post-processing of lines of popular characters. The post-processing unit can also prioritize post-processing of lines of characters with high market value. Furthermore, the post-processing unit can adjust the post-processing method based on the market value of the character. This makes it possible to adjust the post-processing method based on the market value of the character.

[0065] The revenue unit can propose an optimal pricing plan based on the frequency of use of the user. The revenue unit proposes an optimal pricing plan based on, for example, the frequency of use of the user. For example, if the user uses the service frequently, the revenue unit can propose a flat-rate plan. Also, if the user uses the service occasionally, the revenue unit can propose a pay-as-you-go plan. Furthermore, the revenue unit can propose a customized pricing plan based on the frequency of use of the user. This makes it possible to propose an optimal pricing plan based on the frequency of use of the user.

[0066] The revenue unit can analyze the user's past payment history and adjust the fee plan. The revenue unit, for example, analyzes the user's past payment history and adjusts the fee plan. For example, the revenue unit can suggest a discount plan if the user has made large payments in the past. The revenue unit can also suggest a prepayment plan if the user has made late payments in the past. Furthermore, the revenue unit can suggest an optimal fee plan based on the user's past payment history. This makes it possible to adjust the fee plan based on the user's past payment history.

[0067] The revenue unit can propose an optimal pricing plan taking into account the user's geographical location information. The revenue unit, for example, proposes an optimal pricing plan taking into account the user's geographical location information. For example, if the user is in a specific area, the revenue unit can propose a pricing plan specialized for that area. Also, if the user is traveling, the revenue unit can propose a pricing plan that can be used at the user's travel destination. Furthermore, the revenue unit can propose an optimal pricing plan based on the user's geographical location information. This makes it possible to propose an optimal pricing plan based on the user's geographical location information.

[0068] The revenue unit can analyze the user's social media activity and propose relevant pricing plans. The revenue unit, for example, analyzes the user's social media activity and proposes relevant pricing plans. For example, the revenue unit proposes pricing plans related to services the user follows on social media. The revenue unit can also analyze the content of the user's social media posts and propose relevant pricing plans. Furthermore, the revenue unit can propose relevant pricing plans based on the activity of the user's friends on social media. This makes it possible to propose relevant pricing plans based on the user's social media activity.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The reception unit can analyze the user's past selection history and understand the user's tendency toward characters they like. For example, the reception unit can analyze the characteristics of characters the user has previously selected and recommend similar characters. In addition, if the user is interested in a particular genre or work, the reception unit can preferentially display characters related to that genre or work. Furthermore, the reception unit can suggest characters that the user has not yet selected but may be interested in, based on the user's selection history. This enables more personalized character selection based on the user's past selection history.

[0071] The revenue department can provide discount plans limited to specific time periods based on the user's usage. For example, if a user frequently uses the service at night, the revenue department can propose a discount plan limited to nighttime hours. The revenue department can also provide a special weekend plan to users whose usage is concentrated on weekends. Furthermore, the revenue department can propose a discount plan limited to a specific event period to users whose usage increases during that period. This makes it possible to provide flexible pricing plans according to the user's usage.

[0072] The learning unit can combine the characteristics of different characters to generate a new character's speaking style. For example, the learning unit can combine the lines of multiple characters to learn a unique character's speaking style. The learning unit can also combine the characteristics of characters from different genres to generate a character with a new style. Furthermore, the learning unit can generate a new character's speaking style that emphasizes the characteristics of a specific character according to the user's preferences. This can provide a new experience to the user.

[0073] The reception unit can analyze the user's current activity status and suggest the most suitable character selection. For example, if the user is at work, the reception unit can suggest a character that will help the user concentrate. Also, if the user is taking a break, the reception unit can suggest a character that will help the user relax. Furthermore, if the user is exercising, the reception unit can suggest a character that will increase motivation. This makes it possible to select a character according to the user's activity status.

[0074] The learning unit can reflect user feedback in real time and dynamically adjust the learning algorithm. For example, if a user rates a generated text highly, the learning unit immediately reflects that feedback in the learning algorithm. Also, if a user rates it poorly, the learning unit can improve the algorithm based on that feedback. Furthermore, the learning unit can analyze user feedback and continuously improve the accuracy of the learning algorithm. This allows for rapid adjustment of the algorithm based on user feedback.

[0075] The processing flow of the first embodiment will be briefly explained below.

[0076] Step 1: The reception unit receives a character selection from the user. The user can select a character they like, such as a character from an entertainment work. Step 2: The collection unit collects data indicating characteristics of the selected character. For example, the collection unit collects lines of the character from entertainment works. For example, the collection unit can collect lines from anime lines, game scenarios, etc. Step 3: The learning unit learns the character's characteristics based on the collected data. For example, the learning unit learns the character's tone and speaking style based on the collected lines. The learning unit uses generative AI to learn the character's characteristics. Step 4: The preprocessing unit performs preprocessing for text generation based on the learned features. For example, the preprocessing unit gives specific instructions to the generation AI to reflect the character's characteristics. Step 5: The post-processing unit performs post-processing on the generated text, for example, adding character-specific phrases and emotional expressions to the generated text.

[0077] (Example 2) A text generation system according to an embodiment of the present invention generates text in the tone of a character selected by a user. The text generation system learns the characteristics of the character selected by the user and reflects the character's characteristics in the generated text. For example, the text generation system allows a user to select a favorite character and collect lines from entertainment works in which the character appears. The collected lines are then included in a generation AI, which then learns the character's characteristics based on these lines. Next, preprocessing of the text generation is performed to reflect the character's characteristics in the generated results. Furthermore, postprocessing is performed on the generated text to emphasize the character's characteristics and add character-specific phrases and emotional expressions. This allows users to generate text in the tone of their favorite character's speech. The text generation system can also earn revenue by receiving optional usage fees for the generation AI from users. This allows the text generation system to generate text in the tone of a character selected by the user. For example, users can enjoy generating text in the tone of their favorite character's speech. Furthermore, service providers can earn revenue by receiving optional usage fees for the generation AI from users. For example, various pricing plans can be offered, such as monthly fees or fees based on the number of uses.

[0078] A text generation system according to an embodiment includes a reception unit, a collection unit, a learning unit, a preprocessing unit, and a postprocessing unit. The reception unit receives a character selection from a user. The user can select a favorite character, such as a character from an entertainment work. The collection unit collects data indicating characteristics of the selected character. For example, the collection unit collects lines of the character from entertainment works. The collection unit can collect lines from, for example, anime dialogue or game scenarios. The learning unit learns the character's characteristics based on the collected data. For example, the learning unit learns the character's tone and speaking style based on the collected lines. The learning unit learns the character's characteristics using a generation AI. The preprocessing unit performs preprocessing for text generation based on the learned characteristics. For example, the preprocessing unit provides specific instructions to the generation AI to reflect the character's characteristics. The postprocessing unit performs postprocessing on the generated text. For example, the postprocessing unit adds character-specific phrases and emotional expressions to the generated text. This allows the text generation system according to the embodiment to generate text in the tone of voice of the character selected by the user.

[0079] The text generation system includes a revenue unit that receives optional usage fees for the generation AI from users. The revenue unit receives optional usage fees for the generation AI from users. For example, the revenue unit can offer various pricing plans, such as monthly fees or fees based on the number of uses. This allows the service provider to earn revenue by receiving optional usage fees for the generation AI from users.

[0080] The collection unit can collect lines of characters from entertainment works. The collection unit collects lines from, for example, anime lines or game scenarios. For example, the collection unit collects anime lines and uses them as training data for the generation AI. The collection unit can also collect lines from game scenarios and use them as training data for the generation AI. Furthermore, the collection unit can collect lines from movie scripts and use them as training data for the generation AI. This makes it possible to generate text that reflects the characteristics of the characters.

[0081] The learning unit can learn the character's tone of voice and speaking style based on the collected lines. The learning unit, for example, learns the character's tone of voice and speaking style based on the collected lines. For example, the learning unit learns the character's unique phrases and speaking patterns. The learning unit can also learn the character's emotional expressions and writing style. Furthermore, the learning unit can learn the character's pronunciation and intonation. In this way, the character's characteristics can be learned and reflected in text generation.

[0082] The preprocessing unit can give specific instructions to the generation AI to reflect the characteristics of the character. The preprocessing unit can, for example, give specific instructions to the generation AI to reflect the characteristics of the character. For example, the preprocessing unit can give instructions to the generation AI to reflect the character's tone and speaking style. The preprocessing unit can also give instructions to the generation AI to reflect the character's unique phrases and emotional expressions. Furthermore, the preprocessing unit can also give instructions to the generation AI to reflect the character's writing style and pronunciation. This allows the generated text to better reflect the character's characteristics.

[0083] The post-processing unit can add character-specific phrases and emotional expressions to the generated text. For example, the post-processing unit can add character-specific phrases and emotional expressions to the generated text. For example, the post-processing unit can add character-specific phrases. The post-processing unit can also add character emotional expressions. Furthermore, the post-processing unit can emphasize the characteristics of the character's tone and speaking style. This makes the generated text more character-like.

[0084] The reception unit can estimate the user's emotion and customize the character selection interface based on the estimated user's emotion. The reception unit, for example, estimates the user's emotion and customizes the character selection interface based on the estimated user's emotion. For example, if the user is excited, the reception unit can provide a colorful and visually stimulating interface. If the user is relaxed, the reception unit can provide an interface with calm colors and slowly display options. Furthermore, if the user is stressed, the reception unit can provide a simple and intuitive interface and minimize the selection procedure. In this way, an interface can be provided that corresponds to the user's emotion.

[0085] The reception unit can analyze the user's past character selection history and recommend the most suitable character. The reception unit, for example, analyzes the user's past character selection history and recommends the most suitable character. For example, the reception unit may preferentially display characters that the user has frequently selected in the past. The reception unit can also recommend characters that are appropriate for a specific time period or situation based on the user's past selection history. Furthermore, the reception unit can automatically suggest highly relevant characters based on the user's past selection history. This makes it possible to recommend the most suitable character based on the user's past selection history.

[0086] The reception unit can filter characters based on the user's current interests and trends when selecting a character. For example, the reception unit can display related characters based on keywords recently searched by the user. The reception unit can also analyze the user's social media activities and recommend characters that match current trends. Furthermore, the reception unit can filter characters based on trends in online communities in which the user participates. This allows characters to be filtered based on the user's interests and trends.

[0087] The reception unit can provide an optimal selection means according to the user's input method when selecting a character. For example, the reception unit can provide an optimal selection means according to the user's input method when selecting a character. For example, when the user uses voice input, the reception unit can use voice recognition technology to enable the user to select a character. Furthermore, when the user uses text input, the reception unit can search for and display characters based on input keywords. Furthermore, when the user uses image input, the reception unit can use image recognition technology to identify characters and display them as options. This makes it possible to provide an optimal selection means according to the user's input method.

[0088] The reception unit can estimate the user's emotions and determine the priority of character selection based on the estimated user's emotions. The reception unit, for example, estimates the user's emotions and determines the priority of character selection based on the estimated user's emotions. For example, the reception unit can preferentially display popular characters when the user is excited. The reception unit can also preferentially display calm characters when the user is relaxed. Furthermore, the reception unit can also preferentially display soothing characters when the user is feeling stressed. In this way, the priority of character selection can be determined according to the user's emotions.

[0089] The reception unit can prioritize displaying highly relevant characters in consideration of the user's geographical location information when selecting a character. For example, the reception unit prioritizes displaying highly relevant characters in consideration of the user's geographical location information when selecting a character. For example, if the user is in a specific area, the reception unit can prioritize displaying characters related to that area. Furthermore, if the user is traveling, the reception unit can also prioritize displaying characters related to the travel destination. Furthermore, if the user is participating in a specific event, the reception unit can also prioritize displaying characters related to the event. In this way, highly relevant characters can be displayed based on the user's geographical location information.

[0090] The reception unit can analyze the user's social media activity and recommend related characters when selecting a character. For example, the reception unit can analyze the user's social media activity and recommend related characters when selecting a character. For example, the reception unit can preferentially display characters that the user follows on social media. The reception unit can also analyze the content of the user's social media posts and recommend related characters. Furthermore, the reception unit can recommend related characters by referring to the activities of the user's friends on social media. This makes it possible to recommend related characters based on the user's social media activity.

[0091] The reception unit can customize the selection method by reflecting the user's past feedback when selecting a character. For example, the reception unit customizes the selection method by reflecting the user's past feedback when selecting a character. For example, the reception unit preferentially displays characters that the user has previously rated highly. The reception unit can also customize the selection interface based on the user's past feedback. Furthermore, the reception unit can also display characters that the user has previously rated poorly, excluding such characters. This allows the selection method to be customized based on the user's past feedback.

[0092] The collection unit can estimate the user's emotions and adjust the timing of collecting dialogue based on the estimated user's emotions. The collection unit, for example, estimates the user's emotions and adjusts the timing of collecting dialogue based on the estimated user's emotions. For example, the collection unit collects dialogue at a slow pace when the user is relaxed. Also, the collection unit can collect dialogue quickly when the user is in a hurry. Furthermore, the collection unit can preferentially collect visually stimulating dialogue when the user is excited. This makes it possible to adjust the timing of collecting dialogue according to the user's emotions.

[0093] The collection unit can select the optimal collection method depending on the type of entertainment work. The collection unit selects the optimal collection method depending on, for example, the type of entertainment work. For example, in the case of an anime, the collection unit collects lines based on subtitle data. In addition, in the case of a game, the collection unit can also collect lines based on scenario data. Furthermore, in the case of a movie, the collection unit can also collect lines based on script data. This makes it possible to select the optimal collection method depending on the type of entertainment work.

[0094] The collection unit can filter lines based on the scene and situation in which the character appears when collecting the lines. For example, the collection unit filters lines based on the scene and situation in which the character appears when collecting the lines. For example, the collection unit prioritizes collecting lines spoken by a character in an important scene. The collection unit can also prioritize collecting lines in scenes in which a character expresses a particular emotion. Furthermore, the collection unit can also prioritize collecting lines in scenes in which a character is conversing with other characters. This makes it possible to collect lines based on the scene and situation in which a character appears.

[0095] The collection unit can provide an optimal collection means depending on the user's input method when collecting lines. For example, the collection unit provides an optimal collection means depending on the user's input method when collecting lines. For example, when the user uses voice input, the collection unit collects lines using voice recognition technology. Also, when the user uses text input, the collection unit can search for and collect lines based on the input keywords. Furthermore, when the user uses image input, the collection unit can identify a character using image recognition technology and collect the character's lines. This makes it possible to provide an optimal collection means depending on the user's input method.

[0096] The collection unit can estimate the user's emotions and determine the priority of lines to be collected based on the estimated user's emotions. The collection unit, for example, estimates the user's emotions and determines the priority of lines to be collected based on the estimated user's emotions. For example, if the user is excited, the collection unit can preferentially collect lines from action scenes. Also, if the user is relaxed, the collection unit can preferentially collect lines from everyday scenes. Furthermore, if the user is feeling stressed, the collection unit can preferentially collect soothing lines. In this way, the priority of lines can be determined according to the user's emotions.

[0097] When collecting lines, the collection unit can prioritize collecting highly relevant lines by taking into account the user's geographical location information. For example, when collecting lines, the collection unit prioritizes collecting highly relevant lines by taking into account the user's geographical location information. For example, when the user is in a specific area, the collection unit can prioritize collecting lines related to that area. Also, when the user is traveling, the collection unit can prioritize collecting lines related to the travel destination. Furthermore, when the user is participating in a specific event, the collection unit can prioritize collecting lines related to the event. In this way, highly relevant lines can be collected based on the user's geographical location information.

[0098] The collection unit can analyze the user's social media activities and collect related lines when collecting lines. For example, the collection unit analyzes the user's social media activities and collects related lines when collecting lines. For example, the collection unit prioritizes collecting lines of characters the user follows on social media. The collection unit can also analyze the content of the user's social media posts and collect related lines. Furthermore, the collection unit can collect related lines by referring to the activities of the user's friends on social media. This makes it possible to collect related lines based on the user's social media activities.

[0099] The collection unit can customize the collection method by reflecting the user's past feedback when collecting lines. For example, the collection unit customizes the collection method by reflecting the user's past feedback when collecting lines. For example, the collection unit preferentially collects lines that the user has previously rated highly. The collection unit can also customize the collection interface based on the user's past feedback. Furthermore, the collection unit can also collect lines that the user has previously rated poorly, excluding these lines. This allows the collection method to be customized based on the user's past feedback.

[0100] The learning unit can estimate the user's emotions and select learning data based on the estimated user's emotions. The learning unit, for example, estimates the user's emotions and selects learning data based on the estimated user's emotions. For example, if the user is relaxed, the learning unit selects lines from everyday scenes as learning data. Also, if the user is excited, the learning unit can select lines from action scenes as learning data. Furthermore, if the user is feeling stressed, the learning unit can select soothing lines as learning data. This makes it possible to select learning data according to the user's emotions.

[0101] The learning unit can optimize the learning algorithm by referring to past learning data during learning. For example, the learning unit optimizes the learning algorithm by referring to past learning data during learning. For example, the learning unit adjusts the parameters of the learning algorithm based on the past learning data. The learning unit can also extract effective learning patterns from the past learning data and reflect them in the algorithm. Furthermore, the learning unit can analyze the past learning data and improve the accuracy of the learning algorithm. This makes it possible to optimize the learning algorithm by referring to past learning data.

[0102] The learning unit can analyze changes in a character's tone of voice and speaking style during learning and update the learning data. For example, the learning unit analyzes changes in a character's tone of voice and speaking style during learning and update the learning data. For example, if a character's tone of voice changes, the learning unit reflects the change in the learning data. Also, if a character's speaking style changes, the learning unit can also reflect the change in the learning data. Furthermore, if a new line is added to the character, the learning unit can add the line to the learning data. This makes it possible to update the learning data in response to changes in a character's tone of voice and speaking style.

[0103] The learning unit can adjust the learning algorithm by reflecting user feedback during learning. For example, the learning unit adjusts the learning algorithm by reflecting user feedback during learning. For example, the learning unit adjusts the learning algorithm based on generation results that the user has given a high rating. The learning unit can also improve the learning algorithm based on generation results that the user has given a low rating. Furthermore, the learning unit can analyze user feedback and improve the accuracy of the learning algorithm. This makes it possible to adjust the learning algorithm based on user feedback.

[0104] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user's emotions. The learning unit, for example, estimates the user's emotions and adjusts the frequency of learning based on the estimated user's emotions. For example, the learning unit can increase the frequency of learning when the user is excited. The learning unit can also decrease the frequency of learning when the user is relaxed. Furthermore, the learning unit can adjust the frequency of learning to reduce the burden on the user when the user is feeling stressed. This makes it possible to adjust the frequency of learning according to the user's emotions.

[0105] The learning unit can weight the learning data based on the time of submission of the lines during learning. For example, the learning unit weights the learning data based on the time of submission of the lines during learning. For example, the learning unit weights the learning data by assigning a high weight to recently submitted lines. The learning unit can also weight older lines by assigning a low weight to older lines during learning. Furthermore, the learning unit can dynamically adjust the weight of lines based on the time of submission. This makes it possible to weight the learning data based on the time of submission of the lines.

[0106] The learning unit can integrate information from different data sources to expand the training data during training. For example, the learning unit can integrate information from different data sources to expand the training data during training. For example, the learning unit collects and integrates lines from different data sources such as anime, games, and movies. The learning unit can also expand the training data based on information from different data sources. Furthermore, the learning unit can integrate information from different data sources to improve the accuracy of the learning algorithm. This makes it possible to expand the training data by integrating information from different data sources.

[0107] The learning unit can improve the accuracy of learning by referring to literature related to the character during learning. For example, the learning unit can improve the accuracy of learning by referring to literature related to the character during learning. For example, the learning unit can complement the learning data by referring to official character setting materials. The learning unit can also adjust the learning algorithm based on literature related to the character. Furthermore, the learning unit can improve the accuracy of the learning data by referring to literature related to the character. As a result, the accuracy of learning is improved by referring to literature related to the character.

[0108] The preprocessing unit can estimate the user's emotion and adjust the preprocessing method based on the estimated user's emotion. The preprocessing unit, for example, estimates the user's emotion and adjusts the preprocessing method based on the estimated user's emotion. For example, the preprocessing unit can perform preprocessing at a slow pace when the user is relaxed. The preprocessing unit can also perform preprocessing quickly when the user is in a hurry. Furthermore, the preprocessing unit can also perform visually stimulating preprocessing when the user is excited. This makes it possible to adjust the preprocessing method according to the user's emotion.

[0109] The pre-processing unit can perform filtering to emphasize the characteristics of a character's tone of voice and speaking style during pre-processing. The pre-processing unit, for example, performs filtering to emphasize the characteristics of a character's tone of voice and speaking style during pre-processing. For example, the pre-processing unit performs filtering to emphasize the unique tone of voice of a character. The pre-processing unit can also perform filtering to emphasize the characteristics of a character's speaking style. Furthermore, the pre-processing unit can also perform filtering to emphasize the emotional expressions of a character. This makes it possible to perform filtering to emphasize the characteristics of a character's tone of voice and speaking style.

[0110] During preprocessing, the preprocessing unit can provide instructions for generating text based on the scene and situation in which the character appears. During preprocessing, the preprocessing unit, for example, provides instructions for generating text based on the scene and situation in which the character appears. For example, the preprocessing unit provides instructions for generating text based on lines spoken by a character in an important scene. The preprocessing unit can also provide instructions for generating text based on lines spoken in a scene in which the character expresses a particular emotion. Furthermore, the preprocessing unit can also provide instructions for generating text based on lines spoken in a scene in which the character is conversing with another character. This makes it possible to provide instructions for generating text based on the scene and situation in which the character appears.

[0111] The preprocessing unit can improve the accuracy of preprocessing by referring to the user's past generation results during preprocessing. For example, the preprocessing unit improves the accuracy of preprocessing by referring to the user's past generation results during preprocessing. For example, the preprocessing unit improves the accuracy of preprocessing based on generation results that the user has given a high rating. The preprocessing unit can also improve the preprocessing method based on generation results that the user has given a low rating. Furthermore, the preprocessing unit can analyze the user's past generation results and improve the accuracy of preprocessing. In this way, the accuracy of preprocessing is improved by referring to the user's past generation results.

[0112] The preprocessing unit can estimate the user's emotions and determine the priority of preprocessing based on the estimated user's emotions. The preprocessing unit, for example, estimates the user's emotions and determines the priority of preprocessing based on the estimated user's emotions. For example, if the user is excited, the preprocessing unit can preferentially preprocess lines from action scenes. Also, if the user is relaxed, the preprocessing unit can preferentially preprocess lines from everyday scenes. Furthermore, if the user is feeling stressed, the preprocessing unit can preferentially preprocess lines that are soothing. This makes it possible to determine the priority of preprocessing based on the user's emotions.

[0113] The preprocessing unit can provide instructions for text generation taking into account the geographical background of the character during preprocessing. For example, the preprocessing unit provides instructions for text generation taking into account the geographical background of the character during preprocessing. For example, the preprocessing unit provides instructions for text generation based on lines spoken by the character related to a specific region. Furthermore, if the character is traveling, the preprocessing unit can also provide instructions for text generation based on lines related to the travel destination. Furthermore, if the character is participating in a specific event, the preprocessing unit can also provide instructions for text generation based on lines related to the event. This makes it possible to provide instructions for text generation based on the geographical background of the character.

[0114] The preprocessing unit may improve the accuracy of the preprocessing by referring to literature related to the character during preprocessing. For example, the preprocessing unit may improve the accuracy of the preprocessing by referring to literature related to the character during preprocessing. For example, the preprocessing unit may improve the accuracy of the preprocessing by referring to official character setting materials. The preprocessing unit may also adjust the preprocessing method based on literature related to the character. Furthermore, the preprocessing unit may improve the accuracy of the preprocessing by referring to literature related to the character. In this way, the accuracy of the preprocessing is improved by referring to literature related to the character.

[0115] The preprocessing unit can adjust the preprocessing method during preprocessing, taking into account the market value of the character. For example, the preprocessing unit adjusts the preprocessing method during preprocessing, taking into account the market value of the character. For example, the preprocessing unit prioritizes preprocessing of lines of popular characters. The preprocessing unit can also prioritize preprocessing of lines of characters with high market value. Furthermore, the preprocessing unit can adjust the preprocessing method based on the market value of the character. This makes it possible to adjust the preprocessing method based on the market value of the character.

[0116] The post-processing unit can estimate the user's emotion and adjust the post-processing method based on the estimated user's emotion. For example, the post-processing unit can estimate the user's emotion and adjust the post-processing method based on the estimated user's emotion. For example, the post-processing unit can perform post-processing at a slow pace when the user is relaxed. Furthermore, the post-processing unit can perform post-processing quickly when the user is in a hurry. Furthermore, the post-processing unit can perform visually stimulating post-processing when the user is excited. This makes it possible to adjust the post-processing method according to the user's emotion.

[0117] The post-processing unit can perform filtering during post-processing to emphasize phrases and emotional expressions unique to a character. For example, the post-processing unit performs filtering during post-processing to emphasize phrases and emotional expressions unique to a character. For example, the post-processing unit performs filtering to emphasize phrases unique to a character. The post-processing unit can also perform filtering to emphasize emotional expressions of a character. Furthermore, the post-processing unit can also perform filtering to emphasize the characteristics of a character's tone of voice or speaking style. This makes it possible to perform filtering to emphasize phrases and emotional expressions unique to a character.

[0118] The post-processing unit can modify the text during post-processing based on the scene and situation in which the character appears. For example, the post-processing unit modifies the text during post-processing based on the scene and situation in which the character appears. For example, the post-processing unit modifies the text based on lines spoken by the character in an important scene. The post-processing unit can also modify the text based on lines spoken in a scene in which the character expresses a particular emotion. Furthermore, the post-processing unit can also modify the text based on lines spoken in a scene in which the character is conversing with another character. This makes it possible to modify the text based on the scene and situation in which the character appears.

[0119] The post-processing unit can improve the accuracy of post-processing by referring to the user's past generation results during post-processing. For example, the post-processing unit improves the accuracy of post-processing by referring to the user's past generation results during post-processing. For example, the post-processing unit improves the accuracy of post-processing based on generation results that the user has given a high rating. The post-processing unit can also improve the post-processing method based on generation results that the user has given a low rating. Furthermore, the post-processing unit can analyze the user's past generation results and improve the accuracy of post-processing. In this way, the accuracy of post-processing is improved by referring to the user's past generation results.

[0120] The post-processing unit can estimate the user's emotions and determine the priority of post-processing based on the estimated user's emotions. The post-processing unit, for example, estimates the user's emotions and determines the priority of post-processing based on the estimated user's emotions. For example, if the user is excited, the post-processing unit can prioritize post-processing of lines from action scenes. Also, if the user is relaxed, the post-processing unit can prioritize post-processing of lines from everyday scenes. Furthermore, if the user is feeling stressed, the post-processing unit can prioritize post-processing of soothing lines. This makes it possible to determine the priority of post-processing according to the user's emotions.

[0121] The post-processing unit can modify text during post-processing, taking into account the geographical background of the character. For example, the post-processing unit modifies text during post-processing, taking into account the geographical background of the character. For example, the post-processing unit modifies text based on lines that the character has spoken related to a specific region. In addition, if the character is traveling, the post-processing unit can also modify text based on lines that are related to the travel destination. Furthermore, if the character is participating in a specific event, the post-processing unit can also modify text based on lines that are related to the event. This makes it possible to modify text based on the geographical background of the character.

[0122] The post-processing unit may improve the accuracy of post-processing by referring to literature related to the character during post-processing. For example, the post-processing unit may improve the accuracy of post-processing by referring to literature related to the character during post-processing. For example, the post-processing unit may improve the accuracy of post-processing by referring to official character setting materials. The post-processing unit may also adjust the post-processing method based on the literature related to the character. Furthermore, the post-processing unit may improve the accuracy of post-processing by referring to literature related to the character. In this way, the accuracy of post-processing is improved by referring to literature related to the character.

[0123] The post-processing unit can adjust the post-processing method during post-processing, taking into account the market value of the character. For example, the post-processing unit adjusts the post-processing method during post-processing, taking into account the market value of the character. For example, the post-processing unit prioritizes post-processing of lines of popular characters. The post-processing unit can also prioritize post-processing of lines of characters with high market value. Furthermore, the post-processing unit can adjust the post-processing method based on the market value of the character. This makes it possible to adjust the post-processing method based on the market value of the character.

[0124] The revenue unit can estimate the user's emotions and customize a pricing plan based on the estimated user's emotions. The revenue unit, for example, estimates the user's emotions and customizes a pricing plan based on the estimated user's emotions. For example, the revenue unit can provide special offers or discounts when the user is excited. The revenue unit can also suggest a long-term usage plan when the user is relaxed. Furthermore, the revenue unit can suggest an easy-to-use plan when the user is stressed. This makes it possible to customize a pricing plan according to the user's emotions.

[0125] The revenue unit can propose an optimal pricing plan based on the frequency of use of the user. The revenue unit proposes an optimal pricing plan based on, for example, the frequency of use of the user. For example, if the user uses the service frequently, the revenue unit can propose a flat-rate plan. Also, if the user uses the service occasionally, the revenue unit can propose a pay-as-you-go plan. Furthermore, the revenue unit can propose a customized pricing plan based on the frequency of use of the user. This makes it possible to propose an optimal pricing plan based on the frequency of use of the user.

[0126] The revenue unit can analyze the user's past payment history and adjust the fee plan. The revenue unit, for example, analyzes the user's past payment history and adjusts the fee plan. For example, the revenue unit can suggest a discount plan if the user has made large payments in the past. The revenue unit can also suggest a prepayment plan if the user has made late payments in the past. Furthermore, the revenue unit can suggest an optimal fee plan based on the user's past payment history. This makes it possible to adjust the fee plan based on the user's past payment history.

[0127] The revenue unit can estimate the user's emotions and determine the priority of pricing plans based on the estimated user's emotions. The revenue unit, for example, estimates the user's emotions and determines the priority of pricing plans based on the estimated user's emotions. For example, if the user is excited, the revenue unit can preferentially provide special offers or discounts. Furthermore, if the user is relaxed, the revenue unit can preferentially suggest long-term usage plans. Furthermore, if the user is stressed, the revenue unit can preferentially suggest plans that are easy to use. This makes it possible to determine the priority of pricing plans according to the user's emotions.

[0128] The revenue unit can propose an optimal pricing plan taking into account the user's geographical location information. The revenue unit, for example, proposes an optimal pricing plan taking into account the user's geographical location information. For example, if the user is in a specific area, the revenue unit can propose a pricing plan specialized for that area. Also, if the user is traveling, the revenue unit can propose a pricing plan that can be used at the user's travel destination. Furthermore, the revenue unit can propose an optimal pricing plan based on the user's geographical location information. This makes it possible to propose an optimal pricing plan based on the user's geographical location information.

[0129] The revenue unit can analyze the user's social media activity and propose relevant pricing plans. The revenue unit, for example, analyzes the user's social media activity and proposes relevant pricing plans. For example, the revenue unit proposes pricing plans related to services the user follows on social media. The revenue unit can also analyze the content of the user's social media posts and propose relevant pricing plans. Furthermore, the revenue unit can propose relevant pricing plans based on the activity of the user's friends on social media. This makes it possible to propose relevant pricing plans based on the user's social media activity. === Hard Collateral 1-1 === Each of the multiple elements, including the reception unit, collection unit, learning unit, preprocessing unit, post-processing unit, and profit unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives a character selection from a user. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects data indicating the characteristics of the selected character. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns the character's characteristics based on the collected data. The preprocessing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs preprocessing for text generation based on the learned characteristics. The post-processing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs post-processing on the generated text. The profit unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and receives an option usage fee for the generation AI from the user. === Hard Collateral 1-2 === Each of the multiple elements, including the reception unit, collection unit, learning unit, preprocessing unit, post-processing unit, and revenue unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives a character selection from a user. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects data indicating the characteristics of the selected character. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns the character's characteristics based on the collected data. The preprocessing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs preprocessing for text generation based on the learned characteristics. The post-processing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs post-processing on the generated text. The revenue unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and receives an option usage fee for the generation AI from the user. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned reception unit, collection unit, learning unit, preprocessing unit, post-processing unit, and revenue unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314 and receives a character selection from a user. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects data indicating the characteristics of the selected character. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns the character's characteristics based on the collected data. The preprocessing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs preprocessing for text generation based on the learned characteristics. The post-processing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs post-processing on the generated text. The revenue unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and receives an option usage fee for the generation AI from the user. === Hard Collateral 1-4 === Each of the multiple elements, including the reception unit, collection unit, learning unit, preprocessing unit, post-processing unit, and profit-making unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives a character selection from a user. The collection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects data indicating the characteristics of the selected character. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns the character's characteristics based on the collected data. The preprocessing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs preprocessing for text generation based on the learned characteristics. The post-processing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs post-processing on the generated text. The profit-making unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and receives an option usage fee for the generation AI from the user.

[0130] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0131] The reception unit can analyze the user's past selection history and understand the user's tendency toward characters they like. For example, the reception unit can analyze the characteristics of characters the user has previously selected and recommend similar characters. In addition, if the user is interested in a particular genre or work, the reception unit can preferentially display characters related to that genre or work. Furthermore, the reception unit can suggest characters that the user has not yet selected but may be interested in, based on the user's selection history. This enables more personalized character selection based on the user's past selection history.

[0132] The revenue department can provide discount plans limited to specific time periods based on the user's usage. For example, if a user frequently uses the service at night, the revenue department can propose a discount plan limited to nighttime hours. The revenue department can also provide a special weekend plan to users whose usage is concentrated on weekends. Furthermore, the revenue department can propose a discount plan limited to a specific event period to users whose usage increases during that period. This makes it possible to provide flexible pricing plans according to the user's usage.

[0133] The collection unit can estimate the user's emotions and adjust the types of lines to be collected based on the estimated user's emotions. For example, if the user is sad, the collection unit can prioritize collecting lines from moving scenes. Also, if the user is happy, the collection unit can prioritize collecting lines from humorous scenes. Furthermore, if the user is angry, the collection unit can prioritize collecting lines from scenes expressing intense emotions. This makes it possible to collect lines according to the user's emotions.

[0134] The learning unit can combine the characteristics of different characters to generate a new character's speaking style. For example, the learning unit can combine the lines of multiple characters to learn a unique character's speaking style. The learning unit can also combine the characteristics of characters from different genres to generate a character with a new style. Furthermore, the learning unit can generate a new character's speaking style that emphasizes the characteristics of a specific character according to the user's preferences. This can provide a new experience to the user.

[0135] The preprocessing unit can estimate the user's emotion and adjust the style of text generation based on the estimated user's emotion. For example, if the user is relaxed, the preprocessing unit can generate text in a calm tone. If the user is excited, the preprocessing unit can also generate text in an energetic tone. Furthermore, if the user is sad, the preprocessing unit can generate text in an emotional tone. This enables text generation according to the user's emotion.

[0136] The post-processing unit can add specific effects to the generated text based on the user's emotions. For example, the post-processing unit can add bright colors or decorations to the text if the user is happy. The post-processing unit can also add subdued colors or simple decorations to the text if the user is sad. Furthermore, the post-processing unit can add dynamic effects to the text if the user is excited. This allows for visual enhancement of the text according to the user's emotions.

[0137] The reception unit can analyze the user's current activity status and suggest the most suitable character selection. For example, if the user is at work, the reception unit can suggest a character that will help the user concentrate. Also, if the user is taking a break, the reception unit can suggest a character that will help the user relax. Furthermore, if the user is exercising, the reception unit can suggest a character that will increase motivation. This makes it possible to select a character according to the user's activity status.

[0138] The collection unit can estimate the user's emotions and adjust the type of data to be collected based on the estimated user's emotions. For example, if the user is relaxed, the collection unit can preferentially collect data of calm scenes. Also, if the user is excited, the collection unit can preferentially collect data of action scenes. Furthermore, if the user is sad, the collection unit can preferentially collect data of moving scenes. This makes it possible to collect data according to the user's emotions.

[0139] The learning unit can reflect user feedback in real time and dynamically adjust the learning algorithm. For example, if a user rates a generated text highly, the learning unit immediately reflects that feedback in the learning algorithm. Also, if a user rates it poorly, the learning unit can improve the algorithm based on that feedback. Furthermore, the learning unit can analyze user feedback and continuously improve the accuracy of the learning algorithm. This allows for rapid adjustment of the algorithm based on user feedback.

[0140] The post-processing unit can add specific audio effects to the generated text based on the user's emotions. For example, the post-processing unit can add cheerful music or sound effects if the user is happy. The post-processing unit can also add calming music or sound effects if the user is sad. Furthermore, the post-processing unit can add energetic music or sound effects if the user is excited. This makes it possible to add audio effects according to the user's emotions.

[0141] The processing flow of the second embodiment will be briefly explained below.

[0142] Step 1: The reception unit receives a character selection from the user. The user can select a character they like, such as a character from an entertainment work. Step 2: The collection unit collects data indicating characteristics of the selected character. For example, the collection unit collects lines of the character from entertainment works. For example, the collection unit can collect lines from anime lines, game scenarios, etc. Step 3: The learning unit learns the character's characteristics based on the collected data. For example, the learning unit learns the character's tone and speaking style based on the collected lines. The learning unit uses generative AI to learn the character's characteristics. Step 4: The preprocessing unit performs preprocessing for text generation based on the learned features. For example, the preprocessing unit gives specific instructions to the generation AI to reflect the character's characteristics. Step 5: The post-processing unit performs post-processing on the generated text, for example, adding character-specific phrases and emotional expressions to the generated text.

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0147] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0148] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0154] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0157] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0161] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0163] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0164] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0165] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0166] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0167] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0169] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0170] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0171] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0172] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0173] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0174] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0175] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0176] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0177] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0178] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0179] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0180] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0181] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0182] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0183] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0184] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0185] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0186] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0187] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0188] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0189] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0190] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0191] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0192] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0193] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0194] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0195] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0196] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0197] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0198] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0199] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0200] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0201] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0202] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0203] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0204] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0205] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0206] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0207] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0208] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0209] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0210] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0211] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0212] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0213] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0214] [Explanation of symbols]

[0215] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives character selection from a user; a collection unit that collects data indicating characteristics of the character selected by the reception unit; a learning unit that learns the characteristics of a character based on the data collected by the collection unit; a preprocessing unit that performs preprocessing for text generation based on the features learned by the learning unit; a post-processing unit that performs post-processing on the text generated by the pre-processing unit; Equipped with A system characterized by:

2. Equipped with a revenue department that receives optional usage fees for the generated AI from users 2. The system of claim 1.

3. The collecting unit Collect character lines from entertainment works 2. The system of claim 1.

4. The learning unit Learn the character's tone and speaking style based on collected lines 2. The system of claim 1.

5. The pre-treatment unit Give specific instructions to the generated AI to reflect the character's characteristics 2. The system of claim 1.

6. The post-processing unit Add character-specific phrases and emotes to generated text 2. The system of claim 1.

7. The reception unit Estimate the user's emotions and customize the character selection interface based on the estimated user emotions.

2. The system of claim 1.

8. The reception unit Analyze the user's character selection history and recommend the most suitable character 2. The system of claim 1.

9. The reception unit Filter character selection based on the user's current interests and trends 2. The system of claim 1.

Images